Yizhang Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yizhang Liu has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Yanping Li
MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China
7 shared publications - Taotao Lai
Fujian Provincial Key Laboratory of Information Processing and Intelligent Control, School of Computer and Big Data, Minjiang University, Fuzhou, China
6 shared publications - Zuoyong Li
Minjiang University
5 shared publications - Duoqian Miao
School of Computer Science and Technology, Tongji University, Shanghai, China
4 shared publications - Shengjie Zhao
Tongji University, Shanghai, China
4 shared publications - Cairong Zhao
School of Computer Science and Technology, Tongji University, Shanghai, China
3 shared publications
Latest Publications
- 30 April 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 345
FreqAlign: Bidirectional frequency alignment for mitigating contextual hallucinations in LLM-based extractive QA
- 30 April 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 345
FreqAlign: Bidirectional frequency alignment for mitigating contextual hallucinations in LLM-based extractive QA
- 31 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33 (10709908) , 1461-1465
CCTformer: Calibrated Context-Aware Transformer for Correspondence Pruning
Correspondence pruning is a core problem in computer vision, aiming to distinguish correct matches from a large set of initial correspondences. Recent Transformer-based methods, such as VSFormer, have shown remarkable performance by jointly modeling visual appearance and spatial relationships. Nevertheless, these methods often depend on abstract, scene-level visual representations, which are insufficiently precise for validating individual correspondences. In addition, their context aggregation modules often struggle to capture multi-granularity corresponding features, particularly under complex geometric variations. To overcome these limitations, we propose the Calibrated Context-aware Transformer with two key components. The Calibrated Visual Cues Extractor samples features directly at putative match locations to provide well-aligned, correspondence-specific visual cues. The Dual-Perspective Graph Transformer replaces conventional graph attention to better model both node-level and edge-level interactions. Together, these modules enable more robust local-global context fusion. Extensive experiments on YFCC100 M and SUN3D show that CCTformer consistently outperforms the baseline and other state-of-the-art methods.
- 31 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33 (10709908) , 1461-1465
CCTformer: Calibrated Context-Aware Transformer for Correspondence Pruning
Correspondence pruning is a core problem in computer vision, aiming to distinguish correct matches from a large set of initial correspondences. Recent Transformer-based methods, such as VSFormer, have shown remarkable performance by jointly modeling visual appearance and spatial relationships. Nevertheless, these methods often depend on abstract, scene-level visual representations, which are insufficiently precise for validating individual correspondences. In addition, their context aggregation modules often struggle to capture multi-granularity corresponding features, particularly under complex geometric variations. To overcome these limitations, we propose the Calibrated Context-aware Transformer with two key components. The Calibrated Visual Cues Extractor samples features directly at putative match locations to provide well-aligned, correspondence-specific visual cues. The Dual-Perspective Graph Transformer replaces conventional graph attention to better model both node-level and edge-level interactions. Together, these modules enable more robust local-global context fusion. Extensive experiments on YFCC100 M and SUN3D show that CCTformer consistently outperforms the baseline and other state-of-the-art methods.
- 16 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 2889-2900
UD-Gaussian: Uncertainty-Driven Gaussian Modeling for Occluded Person Re-Identification
Occluded person re-identification aims to address the identification challenges posed by pedestrians obscured by other individuals or objects. Existing methods often rely on incorporating pose or semantic information to improve model performance under occlusion. However, such information often depends on external models with inevitably cross-domain gaps, whose stability is limited in complex occlusion environments and prone to false results. In this paper, we propose a Transformer-based uncertainty-driven Gaussian model, termed as UD-Gaussian. Firstly, to enrich the detailed features of pedestrian images, a high-frequency enhancement module is introduced. The high-frequency components of the pedestrian image are extracted by Discrete Haar Wavelet Transform, and Top-K high-frequency patches are extracted to construct a graph Laplacian matrix to achieve high-frequency graph attention, which is fused with features learned from self-attention to enhance the high-frequency feature representation. Given the uncertainty in pedestrian feature learning induced by occlusion makes it challenging to obtain reliable and stable pedestrian features, we propose a probability distribution learning module. This module establishes a memory bank to build Gaussian distributions for each pedestrian identity and the entropy is introduced as a loss function to encourage the model to generate more deterministic and relatively independent probability distributions, thereby enhancing the discriminative ability of the model across different pedestrian identities. The high-frequency enhancement module provides a solid foundation for the probability distribution learning module, alleviating uncertainty caused by pedestrian images themselves. Experimental results on occluded and holistic person re-identification datasets demonstrate the superiority of the proposed method.
- 16 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 2889-2900
UD-Gaussian: Uncertainty-Driven Gaussian Modeling for Occluded Person Re-Identification
Occluded person re-identification aims to address the identification challenges posed by pedestrians obscured by other individuals or objects. Existing methods often rely on incorporating pose or semantic information to improve model performance under occlusion. However, such information often depends on external models with inevitably cross-domain gaps, whose stability is limited in complex occlusion environments and prone to false results. In this paper, we propose a Transformer-based uncertainty-driven Gaussian model, termed as UD-Gaussian. Firstly, to enrich the detailed features of pedestrian images, a high-frequency enhancement module is introduced. The high-frequency components of the pedestrian image are extracted by Discrete Haar Wavelet Transform, and Top-K high-frequency patches are extracted to construct a graph Laplacian matrix to achieve high-frequency graph attention, which is fused with features learned from self-attention to enhance the high-frequency feature representation. Given the uncertainty in pedestrian feature learning induced by occlusion makes it challenging to obtain reliable and stable pedestrian features, we propose a probability distribution learning module. This module establishes a memory bank to build Gaussian distributions for each pedestrian identity and the entropy is introduced as a loss function to encourage the model to generate more deterministic and relatively independent probability distributions, thereby enhancing the discriminative ability of the model across different pedestrian identities. The high-frequency enhancement module provides a solid foundation for the probability distribution learning module, alleviating uncertainty caused by pedestrian images themselves. Experimental results on occluded and holistic person re-identification datasets demonstrate the superiority of the proposed method.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33, 4331-4335
CGSNet: Cross-Graph Spatial and Sparse Network for Two-View Geometry Estimation
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33, 4331-4335
CGSNet: Cross-Graph Spatial and Sparse Network for Two-View Geometry Estimation
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (10) , 1
Deterministic Model Fitting via Neighborhood Information and Greedy Search
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (10) , 1
Deterministic Model Fitting via Neighborhood Information and Greedy Search
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 1-11
Dynamic Mosaics: Saliency-Guided Adaptive Masking for Occluded Person Re-Identification
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 1-11
Dynamic Mosaics: Saliency-Guided Adaptive Masking for Occluded Person Re-Identification
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8577-8585
Two-View Correspondence Pruning via Channel-Spatial Interaction and Bidirectional Consensus Interaction
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8577-8585
Open AccessTwo-View Correspondence Pruning via Channel-Spatial Interaction and Bidirectional Consensus Interaction
- 28 November 2024
- Published by Elsevier in ISPRS Journal of Photogrammetry and Remote Sensing
- Vol. 219, 38-51
MGCNet: Multi-granularity consensus network for remote sensing image correspondence pruning
- 28 November 2024
- Published by Elsevier in ISPRS Journal of Photogrammetry and Remote Sensing
- Vol. 219, 38-51
MGCNet: Multi-granularity consensus network for remote sensing image correspondence pruning
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 7754-7763
RoSe: Rotation-Invariant Sequence-Aware Consensus for Robust Correspondence Pruning
Correspondence pruning has recently drawn considerable attention as a crucial step in image matching. Existing methods typically achieve this by constructing neighborhoods for each feature point and imposing neighborhood consistency. However, the nearest-neighbor matching strategy often results in numerous many-to-one correspondences, thereby reducing the reliability of neighborhood information. Furthermore, the smoothness constraint fails in cases of large-scale rotations, leading to misjudgments. To address the above issues, this paper proposes a novel robust correspondence pruning method termed RoSe, which is based on rotation-invariant sequence-aware consensus. We formulate the correspondence pruning problem as a mathematical optimization problem and derive a closed-form solution. Specifically, we devise a rectified local neighborhood construction strategy that effectively enlarges the distribution between inliers and outliers. Meanwhile, to accommodate large-scale rotation, we propose a relative sequence-aware consistency as an alternative to existing smoothness constraints, which can better characterize the topological structure of inliers. Experimental results on image matching and registration tasks demonstrate the effectiveness of our method. Robustness analysis involving diverse feature descriptors and varying rotation degrees further showcases the efficacy of our method.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 7754-7763
Open AccessRoSe: Rotation-Invariant Sequence-Aware Consensus for Robust Correspondence Pruning
Correspondence pruning has recently drawn considerable attention as a crucial step in image matching. Existing methods typically achieve this by constructing neighborhoods for each feature point and imposing neighborhood consistency. However, the nearest-neighbor matching strategy often results in numerous many-to-one correspondences, thereby reducing the reliability of neighborhood information. Furthermore, the smoothness constraint fails in cases of large-scale rotations, leading to misjudgments. To address the above issues, this paper proposes a novel robust correspondence pruning method termed RoSe, which is based on rotation-invariant sequence-aware consensus. We formulate the correspondence pruning problem as a mathematical optimization problem and derive a closed-form solution. Specifically, we devise a rectified local neighborhood construction strategy that effectively enlarges the distribution between inliers and outliers. Meanwhile, to accommodate large-scale rotation, we propose a relative sequence-aware consistency as an alternative to existing smoothness constraints, which can better characterize the topological structure of inliers. Experimental results on image matching and registration tasks demonstrate the effectiveness of our method. Robustness analysis involving diverse feature descriptors and varying rotation degrees further showcases the efficacy of our method.
- 30 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33 (10577149) , 3200-3211
Occlusion-Aware Transformer With Second-Order Attention for Person Re-Identification
Person re-identification (ReID) typically encounters varying degrees of occlusion in real-world scenarios. While previous methods have addressed this using handcrafted partitions or external cues, they often compromise semantic information or increase network complexity. In this paper, we propose a new method from a novel perspective, termed as OAT. Specifically, we first use a Transformer backbone with multiple class tokens for diverse pedestrian feature learning. Given that the self-attention mechanism in the Transformer solely focuses on low-level feature correlations, neglecting higher-order relations among different body parts or regions. Thus, we propose the Second-Order Attention (SOA) module to capture more comprehensive features. To address computational efficiency, we further derive approximation formulations for implementing second-order attention. Observing that the importance of semantics associated with different class tokens varies due to the uncertainty of the location and size of occlusion, we propose the Entropy Guided Fusion (EGF) module for multiple class tokens. By conducting uncertainty analysis on each class token, higher weights are assigned to those with lower information entropy, while lower weights are assigned to class tokens with higher entropy. The dynamic weight adjustment can mitigate the impact of occlusion-induced uncertainty on feature learning, thereby facilitating the acquisition of discriminative class token representations. Extensive experiments have been conducted on occluded and holistic person re-identification datasets, which demonstrate the effectiveness of our proposed method.
- 30 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33 (10577149) , 3200-3211
Occlusion-Aware Transformer With Second-Order Attention for Person Re-Identification
Person re-identification (ReID) typically encounters varying degrees of occlusion in real-world scenarios. While previous methods have addressed this using handcrafted partitions or external cues, they often compromise semantic information or increase network complexity. In this paper, we propose a new method from a novel perspective, termed as OAT. Specifically, we first use a Transformer backbone with multiple class tokens for diverse pedestrian feature learning. Given that the self-attention mechanism in the Transformer solely focuses on low-level feature correlations, neglecting higher-order relations among different body parts or regions. Thus, we propose the Second-Order Attention (SOA) module to capture more comprehensive features. To address computational efficiency, we further derive approximation formulations for implementing second-order attention. Observing that the importance of semantics associated with different class tokens varies due to the uncertainty of the location and size of occlusion, we propose the Entropy Guided Fusion (EGF) module for multiple class tokens. By conducting uncertainty analysis on each class token, higher weights are assigned to those with lower information entropy, while lower weights are assigned to class tokens with higher entropy. The dynamic weight adjustment can mitigate the impact of occlusion-induced uncertainty on feature learning, thereby facilitating the acquisition of discriminative class token representations. Extensive experiments have been conducted on occluded and holistic person re-identification datasets, which demonstrate the effectiveness of our proposed method.